BroAlanTaps commited on
Commit
37f53af
1 Parent(s): 55bfb09

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<mem_0>": 50257,
3
+ "<mem_10>": 50267,
4
+ "<mem_11>": 50268,
5
+ "<mem_12>": 50269,
6
+ "<mem_13>": 50270,
7
+ "<mem_14>": 50271,
8
+ "<mem_15>": 50272,
9
+ "<mem_16>": 50273,
10
+ "<mem_17>": 50274,
11
+ "<mem_18>": 50275,
12
+ "<mem_19>": 50276,
13
+ "<mem_1>": 50258,
14
+ "<mem_20>": 50277,
15
+ "<mem_21>": 50278,
16
+ "<mem_22>": 50279,
17
+ "<mem_23>": 50280,
18
+ "<mem_24>": 50281,
19
+ "<mem_25>": 50282,
20
+ "<mem_26>": 50283,
21
+ "<mem_27>": 50284,
22
+ "<mem_28>": 50285,
23
+ "<mem_29>": 50286,
24
+ "<mem_2>": 50259,
25
+ "<mem_30>": 50287,
26
+ "<mem_31>": 50288,
27
+ "<mem_32>": 50289,
28
+ "<mem_33>": 50290,
29
+ "<mem_34>": 50291,
30
+ "<mem_35>": 50292,
31
+ "<mem_36>": 50293,
32
+ "<mem_37>": 50294,
33
+ "<mem_38>": 50295,
34
+ "<mem_39>": 50296,
35
+ "<mem_3>": 50260,
36
+ "<mem_40>": 50297,
37
+ "<mem_41>": 50298,
38
+ "<mem_42>": 50299,
39
+ "<mem_43>": 50300,
40
+ "<mem_44>": 50301,
41
+ "<mem_45>": 50302,
42
+ "<mem_46>": 50303,
43
+ "<mem_47>": 50304,
44
+ "<mem_48>": 50305,
45
+ "<mem_49>": 50306,
46
+ "<mem_4>": 50261,
47
+ "<mem_50>": 50307,
48
+ "<mem_51>": 50308,
49
+ "<mem_52>": 50309,
50
+ "<mem_53>": 50310,
51
+ "<mem_54>": 50311,
52
+ "<mem_55>": 50312,
53
+ "<mem_56>": 50313,
54
+ "<mem_57>": 50314,
55
+ "<mem_58>": 50315,
56
+ "<mem_59>": 50316,
57
+ "<mem_5>": 50262,
58
+ "<mem_60>": 50317,
59
+ "<mem_61>": 50318,
60
+ "<mem_62>": 50319,
61
+ "<mem_63>": 50320,
62
+ "<mem_6>": 50263,
63
+ "<mem_7>": 50264,
64
+ "<mem_8>": 50265,
65
+ "<mem_9>": 50266
66
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,480 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<mem_0>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<mem_1>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<mem_2>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<mem_3>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<mem_4>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<mem_5>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<mem_6>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<mem_7>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<mem_8>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<mem_9>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<mem_10>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "<mem_11>",
82
+ "lstrip": false,
83
+ "normalized": false,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<mem_12>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "<mem_13>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<mem_14>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "<mem_15>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<mem_16>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "<mem_17>",
124
+ "lstrip": false,
125
+ "normalized": false,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<mem_18>",
131
+ "lstrip": false,
132
+ "normalized": false,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "<mem_19>",
138
+ "lstrip": false,
139
+ "normalized": false,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<mem_20>",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "<mem_21>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<mem_22>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "<mem_23>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<mem_24>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "<mem_25>",
180
+ "lstrip": false,
181
+ "normalized": false,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<mem_26>",
187
+ "lstrip": false,
188
+ "normalized": false,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "<mem_27>",
194
+ "lstrip": false,
195
+ "normalized": false,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<mem_28>",
201
+ "lstrip": false,
202
+ "normalized": false,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "<mem_29>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<mem_30>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "<mem_31>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<mem_32>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "<mem_33>",
236
+ "lstrip": false,
237
+ "normalized": false,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<mem_34>",
243
+ "lstrip": false,
244
+ "normalized": false,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "<mem_35>",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<mem_36>",
257
+ "lstrip": false,
258
+ "normalized": false,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "<mem_37>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<mem_38>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "<mem_39>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ },
283
+ {
284
+ "content": "<mem_40>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false
289
+ },
290
+ {
291
+ "content": "<mem_41>",
292
+ "lstrip": false,
293
+ "normalized": false,
294
+ "rstrip": false,
295
+ "single_word": false
296
+ },
297
+ {
298
+ "content": "<mem_42>",
299
+ "lstrip": false,
300
+ "normalized": false,
301
+ "rstrip": false,
302
+ "single_word": false
303
+ },
304
+ {
305
+ "content": "<mem_43>",
306
+ "lstrip": false,
307
+ "normalized": false,
308
+ "rstrip": false,
309
+ "single_word": false
310
+ },
311
+ {
312
+ "content": "<mem_44>",
313
+ "lstrip": false,
314
+ "normalized": false,
315
+ "rstrip": false,
316
+ "single_word": false
317
+ },
318
+ {
319
+ "content": "<mem_45>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false
324
+ },
325
+ {
326
+ "content": "<mem_46>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false
331
+ },
332
+ {
333
+ "content": "<mem_47>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false
338
+ },
339
+ {
340
+ "content": "<mem_48>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false
345
+ },
346
+ {
347
+ "content": "<mem_49>",
348
+ "lstrip": false,
349
+ "normalized": false,
350
+ "rstrip": false,
351
+ "single_word": false
352
+ },
353
+ {
354
+ "content": "<mem_50>",
355
+ "lstrip": false,
356
+ "normalized": false,
357
+ "rstrip": false,
358
+ "single_word": false
359
+ },
360
+ {
361
+ "content": "<mem_51>",
362
+ "lstrip": false,
363
+ "normalized": false,
364
+ "rstrip": false,
365
+ "single_word": false
366
+ },
367
+ {
368
+ "content": "<mem_52>",
369
+ "lstrip": false,
370
+ "normalized": false,
371
+ "rstrip": false,
372
+ "single_word": false
373
+ },
374
+ {
375
+ "content": "<mem_53>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false
380
+ },
381
+ {
382
+ "content": "<mem_54>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false
387
+ },
388
+ {
389
+ "content": "<mem_55>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false
394
+ },
395
+ {
396
+ "content": "<mem_56>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false
401
+ },
402
+ {
403
+ "content": "<mem_57>",
404
+ "lstrip": false,
405
+ "normalized": false,
406
+ "rstrip": false,
407
+ "single_word": false
408
+ },
409
+ {
410
+ "content": "<mem_58>",
411
+ "lstrip": false,
412
+ "normalized": false,
413
+ "rstrip": false,
414
+ "single_word": false
415
+ },
416
+ {
417
+ "content": "<mem_59>",
418
+ "lstrip": false,
419
+ "normalized": false,
420
+ "rstrip": false,
421
+ "single_word": false
422
+ },
423
+ {
424
+ "content": "<mem_60>",
425
+ "lstrip": false,
426
+ "normalized": false,
427
+ "rstrip": false,
428
+ "single_word": false
429
+ },
430
+ {
431
+ "content": "<mem_61>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false
436
+ },
437
+ {
438
+ "content": "<mem_62>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false
443
+ },
444
+ {
445
+ "content": "<mem_63>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false
450
+ }
451
+ ],
452
+ "bos_token": {
453
+ "content": "<|endoftext|>",
454
+ "lstrip": false,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false
458
+ },
459
+ "eos_token": {
460
+ "content": "<|endoftext|>",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false
465
+ },
466
+ "pad_token": {
467
+ "content": "<|endoftext|>",
468
+ "lstrip": false,
469
+ "normalized": true,
470
+ "rstrip": false,
471
+ "single_word": false
472
+ },
473
+ "unk_token": {
474
+ "content": "<|endoftext|>",
475
+ "lstrip": false,
476
+ "normalized": true,
477
+ "rstrip": false,
478
+ "single_word": false
479
+ }
480
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,605 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<mem_0>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<mem_1>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<mem_2>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50260": {
37
+ "content": "<mem_3>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50261": {
45
+ "content": "<mem_4>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50262": {
53
+ "content": "<mem_5>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "50263": {
61
+ "content": "<mem_6>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "50264": {
69
+ "content": "<mem_7>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "50265": {
77
+ "content": "<mem_8>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "50266": {
85
+ "content": "<mem_9>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "50267": {
93
+ "content": "<mem_10>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "50268": {
101
+ "content": "<mem_11>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "50269": {
109
+ "content": "<mem_12>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "50270": {
117
+ "content": "<mem_13>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "50271": {
125
+ "content": "<mem_14>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "50272": {
133
+ "content": "<mem_15>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "50273": {
141
+ "content": "<mem_16>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "50274": {
149
+ "content": "<mem_17>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "50275": {
157
+ "content": "<mem_18>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "50276": {
165
+ "content": "<mem_19>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "50277": {
173
+ "content": "<mem_20>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "50278": {
181
+ "content": "<mem_21>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "50279": {
189
+ "content": "<mem_22>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "50280": {
197
+ "content": "<mem_23>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "50281": {
205
+ "content": "<mem_24>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "50282": {
213
+ "content": "<mem_25>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "50283": {
221
+ "content": "<mem_26>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "50284": {
229
+ "content": "<mem_27>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "50285": {
237
+ "content": "<mem_28>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "50286": {
245
+ "content": "<mem_29>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "50287": {
253
+ "content": "<mem_30>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "50288": {
261
+ "content": "<mem_31>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "50289": {
269
+ "content": "<mem_32>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "50290": {
277
+ "content": "<mem_33>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "50291": {
285
+ "content": "<mem_34>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "50292": {
293
+ "content": "<mem_35>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "50293": {
301
+ "content": "<mem_36>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "50294": {
309
+ "content": "<mem_37>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "50295": {
317
+ "content": "<mem_38>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "50296": {
325
+ "content": "<mem_39>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "50297": {
333
+ "content": "<mem_40>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "50298": {
341
+ "content": "<mem_41>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "50299": {
349
+ "content": "<mem_42>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "50300": {
357
+ "content": "<mem_43>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "50301": {
365
+ "content": "<mem_44>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "50302": {
373
+ "content": "<mem_45>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "50303": {
381
+ "content": "<mem_46>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "50304": {
389
+ "content": "<mem_47>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "50305": {
397
+ "content": "<mem_48>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "50306": {
405
+ "content": "<mem_49>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "50307": {
413
+ "content": "<mem_50>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "50308": {
421
+ "content": "<mem_51>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "50309": {
429
+ "content": "<mem_52>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "50310": {
437
+ "content": "<mem_53>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "50311": {
445
+ "content": "<mem_54>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "50312": {
453
+ "content": "<mem_55>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "50313": {
461
+ "content": "<mem_56>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "50314": {
469
+ "content": "<mem_57>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "50315": {
477
+ "content": "<mem_58>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "50316": {
485
+ "content": "<mem_59>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "50317": {
493
+ "content": "<mem_60>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "50318": {
501
+ "content": "<mem_61>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "50319": {
509
+ "content": "<mem_62>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "50320": {
517
+ "content": "<mem_63>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ }
524
+ },
525
+ "additional_special_tokens": [
526
+ "<mem_0>",
527
+ "<mem_1>",
528
+ "<mem_2>",
529
+ "<mem_3>",
530
+ "<mem_4>",
531
+ "<mem_5>",
532
+ "<mem_6>",
533
+ "<mem_7>",
534
+ "<mem_8>",
535
+ "<mem_9>",
536
+ "<mem_10>",
537
+ "<mem_11>",
538
+ "<mem_12>",
539
+ "<mem_13>",
540
+ "<mem_14>",
541
+ "<mem_15>",
542
+ "<mem_16>",
543
+ "<mem_17>",
544
+ "<mem_18>",
545
+ "<mem_19>",
546
+ "<mem_20>",
547
+ "<mem_21>",
548
+ "<mem_22>",
549
+ "<mem_23>",
550
+ "<mem_24>",
551
+ "<mem_25>",
552
+ "<mem_26>",
553
+ "<mem_27>",
554
+ "<mem_28>",
555
+ "<mem_29>",
556
+ "<mem_30>",
557
+ "<mem_31>",
558
+ "<mem_32>",
559
+ "<mem_33>",
560
+ "<mem_34>",
561
+ "<mem_35>",
562
+ "<mem_36>",
563
+ "<mem_37>",
564
+ "<mem_38>",
565
+ "<mem_39>",
566
+ "<mem_40>",
567
+ "<mem_41>",
568
+ "<mem_42>",
569
+ "<mem_43>",
570
+ "<mem_44>",
571
+ "<mem_45>",
572
+ "<mem_46>",
573
+ "<mem_47>",
574
+ "<mem_48>",
575
+ "<mem_49>",
576
+ "<mem_50>",
577
+ "<mem_51>",
578
+ "<mem_52>",
579
+ "<mem_53>",
580
+ "<mem_54>",
581
+ "<mem_55>",
582
+ "<mem_56>",
583
+ "<mem_57>",
584
+ "<mem_58>",
585
+ "<mem_59>",
586
+ "<mem_60>",
587
+ "<mem_61>",
588
+ "<mem_62>",
589
+ "<mem_63>"
590
+ ],
591
+ "bos_token": "<|endoftext|>",
592
+ "clean_up_tokenization_spaces": true,
593
+ "eos_token": "<|endoftext|>",
594
+ "max_length": 510,
595
+ "model_max_length": 1024,
596
+ "pad_to_multiple_of": null,
597
+ "pad_token": "<|endoftext|>",
598
+ "pad_token_type_id": 0,
599
+ "padding_side": "right",
600
+ "stride": 0,
601
+ "tokenizer_class": "GPT2Tokenizer",
602
+ "truncation_side": "right",
603
+ "truncation_strategy": "longest_first",
604
+ "unk_token": "<|endoftext|>"
605
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff